Skip to content

Commit

Permalink
add SQL script for activity #6238
Browse files Browse the repository at this point in the history
  • Loading branch information
pdurbin committed Oct 2, 2019
1 parent d1d1f89 commit c6683aa
Show file tree
Hide file tree
Showing 2 changed files with 55 additions and 0 deletions.
46 changes: 46 additions & 0 deletions doc/sphinx-guides/source/_static/api/activity.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
create temp view latestdownload as select df.id, max(responsetime) as latest
from datafile df LEFT OUTER JOIN guestbookresponse gbr on df.id=gbr.datafile_id
group by df.id;

-- First, dataverses
select dtype, dv.name as name, owner.name as owner , 'N/A' as downloaded , publicationdate as published
from dataverse dv, dvobject dvo, dataverse owner
where dv.id=dvo.id
and owner.id = dvo.owner_id
and publicationdate is not null
UNION -- datasets
select dtype, dsfv.value as name, owner.name as owner, 'N/A' as downloaded, dsv.releasetime as published
from datasetfieldvalue dsfv, datasetfield dsf, datasetversion dsv, dvobject dvo, dataverse owner
where dsfv.datasetfield_id = dsf.id
and dsf.datasetversion_id = dsv.id
and dsv.dataset_id = dvo.id
and owner.id = dvo.owner_id
and dsf.datasetfieldtype_id=1
and dsv.id in
(select id from datasetversion where
concat(datasetversion.dataset_id,':', datasetversion.versionnumber + (.01 * datasetversion.minorversionnumber)) in
(select concat(datasetversion.dataset_id,':', max(datasetversion.versionnumber + (.01 * datasetversion.minorversionnumber))) as max
from datasetversion
join dataset on dataset.id = datasetversion.dataset_id
where versionstate='RELEASED'
and dataset.harvestingclient_id is null
group by dataset_id))
UNION -- datafile (NEED VIEW)
select dtype, fmd.label as name, dsfv.value as owner, latest::text as downloaded, dsv.releasetime as published
from filemetadata fmd, datasetversion dsv, datasetfieldvalue dsfv, datasetfield dsf, dvobject dvo, latestdownload ld
where fmd.datasetversion_id = dsv.id
and dsv.id = dsf.datasetversion_id
and dsf.id = dsfv.datasetfield_id
and fmd.datafile_id = dvo.id
and dsf.datasetfieldtype_id=1
and fmd.datafile_id = ld.id
and dsv.id in
(select id from datasetversion where
concat(datasetversion.dataset_id,':', datasetversion.versionnumber + (.01 * datasetversion.minorversionnumber)) in
(select concat(datasetversion.dataset_id,':', max(datasetversion.versionnumber + (.01 * datasetversion.minorversionnumber))) as max
from datasetversion
join dataset on dataset.id = datasetversion.dataset_id
where versionstate='RELEASED'
and dataset.harvestingclient_id is null
group by dataset_id))
order by published, owner;
9 changes: 9 additions & 0 deletions doc/sphinx-guides/source/api/metrics.rst
Original file line number Diff line number Diff line change
Expand Up @@ -104,3 +104,12 @@ dataLocation
Specifies whether the metric should query ``local`` data, ``remote`` data (e.g. harvested), or ``all`` data when getting results. Only works for dataset metrics.

Example: ``curl https://demo.dataverse.org/api/info/metrics/datasets/?dataLocation=remote``

Activity
--------

The following script will report the following for published dataverses, datasets, and files: dtype, name, owner, downloaded, published

:download:`activity.sql <../_static/api/activity.sql>`

TODO: add as an API.

0 comments on commit c6683aa

Please sign in to comment.